Instructions to use SupraLabs/reasoning-summarizer-800m-pre with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SupraLabs/reasoning-summarizer-800m-pre with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="SupraLabs/reasoning-summarizer-800m-pre")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("SupraLabs/reasoning-summarizer-800m-pre")
model = AutoModelForCausalLM.from_pretrained("SupraLabs/reasoning-summarizer-800m-pre")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use SupraLabs/reasoning-summarizer-800m-pre with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "SupraLabs/reasoning-summarizer-800m-pre"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SupraLabs/reasoning-summarizer-800m-pre",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/SupraLabs/reasoning-summarizer-800m-pre

SGLang

How to use SupraLabs/reasoning-summarizer-800m-pre with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "SupraLabs/reasoning-summarizer-800m-pre" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SupraLabs/reasoning-summarizer-800m-pre",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "SupraLabs/reasoning-summarizer-800m-pre" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SupraLabs/reasoning-summarizer-800m-pre",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use SupraLabs/reasoning-summarizer-800m-pre with Docker Model Runner:
```
docker model run hf.co/SupraLabs/reasoning-summarizer-800m-pre
```

Demo for this model on Spaces

by multimodalart - opened 1 day ago

Discussion

multimodalart

1 day ago

Hey @SupraLabs 🤗, it's me again, Poli from Hugging Face

You keep shipping 🚢 — congrats on SupraLabs/reasoning-summarizer-800m-pre! Once again, me + my agent built an interactive demo app of it on Hugging Face Spaces, running on a free ZeroGPU infrastructure.

Here's a link to the demo: https://huggingface.co/spaces/hugging-apps/reasoning-summarizer-800m

And you know the spiel, but it would be great to transfer it to your organization/user on Hugging Face. Just let me know which username/org to transfer over, we hope it can give your work more visibility, discoverability and allows folks to try it out.

In the future, feel free to already ship models with demos included. You can use this one as a blueprint to build by yourself or with the help of an agent — you can load the huggingface-spaces skill on Claude Code, Codex, Pi, etc.

(If you have any questions or just want to chat more about this, you can find me on Twitter, LinkedIn or apolinario @ huggingface.co)

Cheers,

Poli

QyrouNnet-AI

SupraLabs org 1 day ago

hey thanks for the demo, we are impressed by the UI and UX

you, can transfer it to SupraLabs org

Your work is well appreciated!

QyrouNnet-AI

SupraLabs org 1 day ago

You can transfer the other demo to our organization too!

could we know why you are doing this for free?

LH-Tech-AI

SupraLabs org 1 day ago

message me on discord please @multimodalart :lh_tech_ai - CU!

multimodalart

about 23 hours ago

•

edited about 22 hours ago

Hey @QyrouNnet-AI

Here's the transferred Space: https://huggingface.co/spaces/SupraLabs/reasoning-summarizer-800m
Feel free to post about, put the demo on the project page, reference it on repos, etc. as you wish

Also, feel more than free to take ownership and make modifications as you see fit. For future releases from you, would be great if they already came with a demos! You can use this one as a blueprint to build by yourself or with the help of an agent, you can load the huggingface-spaces skill on Claude Code, Codex, Pi, etc.

could we know why you are doing this for free?

sure! we are monitoring repos and papers that are getting viral and using an agentic workflow with human-in-the-loop that builds automatically demos for them. We believe the community benefits if artifacts on the Hub (models/papers) have demos/apps associated with them. It's also educational: we hope that in the future you feel empowered to build your own demos for future releases. And it's also a "carrot" not "stick" approach to showcasing the value the Hub can have in case folks want to upgrade to PRO/Team/Enterprise in order to have more quota of compute on ZeroGPU demos/storage/etc :)

QyrouNnet-AI

SupraLabs org about 23 hours ago

Hey @multimodalart , we want you to know that we really appreciate your work!

Also, I am looking forward to upgrading to PRO or team. I find that HuggingFace is truly worth upgrading!

Also, you could help us launch SupraCode!
We are developing a free and open-source coding platform that fully focuses on using local coding models for coding with a convenient UI and UX like Codex or Claude code (UI) with the help of our AI models and tools!

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment